Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instances of the word "show" and its variations, often in the context of demonstrating support or abilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pythag
    -0.47
     zvuky
    -0.47
    lihood
    -0.46
    Nesta
    -0.45
     pleas
    -0.44
    Padding
    -0.43
     Zahl
    -0.43
    Explanation
    -0.41
    gania
    -0.41
     hither
    -0.40
    POSITIVE LOGITS
     commitment
    0.86
     how
    0.85
     seriousness
    0.85
     maturity
    0.82
     prowess
    0.80
     clearly
    0.80
     willingness
    0.79
     versatility
    0.78
     solidarity
    0.78
     typelib
    0.78
    Act Density 0.281%

    No Known Activations